changeset 9:ef3ebaa70032 draft

planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/topic/dada2/tools/dada2 commit a54770771e567c7ad8a9dd75cc4689c3935ef11c
author matthias
date Tue, 28 May 2019 12:13:45 -0400
parents af8d1ccbd153
children 1934b45da33c
files README.md dada2_learnErrors.xml macros.xml test-data/dada2_species.loc test-data/dada2_taxonomy.loc test-data/qualityProfile.pdf test-data/qualityProfileMultiple.pdf test-data/qualityProfileMultiple_rev.pdf test-data/qualityProfileSmallSample.pdf test-data/qualityProfile_rev.pdf tool_data_table_conf.xml.test
diffstat 11 files changed, 59 insertions(+), 9 deletions(-) [+]
line wrap: on
line diff
--- a/README.md	Mon May 27 13:21:48 2019 -0400
+++ b/README.md	Tue May 28 12:13:45 2019 -0400
@@ -11,7 +11,7 @@
 Datatypes
 =========
 
-The dada2 Galaxy wrappers use a few extra data types to ensure that only inputs of the correct type can be used. 
+The dada2 Galaxy wrappers use a few extra data types to ensure that only inputs of the correct type can be used, these datatypes are available from Galaxy release 19.05, for earlier releases they need to be added manually. 
 
 For the outputs of derep, dada, learnErrors, and mergePairs the following datatypes are used that derive from  Rdata (which contains the named list that is returned from the corresponding dada function):
 
@@ -35,5 +35,4 @@
 TODOs 
 =====
 
-- implememt getUniques tool to view intermediate results?
-- implement tests for cached reference data
+- implement getUniques tool to view intermediate results?
--- a/dada2_learnErrors.xml	Mon May 27 13:21:48 2019 -0400
+++ b/dada2_learnErrors.xml	Tue May 28 12:13:45 2019 -0400
@@ -90,7 +90,7 @@
 
 Error rates are learned by alternating between sample inference and error rate estimation until convergence. Additionally a plot is generated that shows the observed frequency of each transition (eg. A->C) as a function of the associated quality score, the final estimated error rates (if they exist), the initial input rates, and the expected error rates under the nominal definition of quality scores.
 
-In addition a plot is generated (with plotErrors) that shows the observed frequency of each transition (eg. A->C) as a function of the associated quality score. Also the final estimated error rates (if they exist) are shown. Optionally also the initial input rates and the expected error rates under the nominal definition of quality scores can be added to the plot. 
+In addition a plot is generated (with plotErrors) that shows the observed frequency of each transition (eg. A->C) as a function of the associated quality score. Also the final estimated error rates (if they exist) are shown. Optionally also the initial input rates and the expected error rates under the nominal definition of quality scores can be added to the plot.
 
 Usage
 .....
@@ -112,7 +112,7 @@
 
 It is expected that the estimated error rates (black lines in the plot) are in a good fit to the observed rates (points in the plot), and that the error rates drop with increased quality. Try to increase the **number of bases to use for learning** if this is not the case.
 
-Error functions: 
+Error functions:
 
 - loessErrfun: accepts a matrix of observed transitions, with each transition corresponding to a row (eg. row 2 = A->C) and each column to a quality score (eg. col 31 = Q30). It returns a matrix of estimated error rates of the same shape. Error rates are estimates by a loess fit of the observed rates of each transition as a function of the quality score. Self-transitions (i.e. A->A) are taken to be the left-over probability.
 - noqualErrfun: accepts a matrix of observed transitions, groups together all observed transitions regardless of quality scores, and estimates the error rate for that transition as the observed fraction of those transitions. The effect is that quality scores will be effectively ignored.
--- a/macros.xml	Mon May 27 13:21:48 2019 -0400
+++ b/macros.xml	Tue May 28 12:13:45 2019 -0400
@@ -26,7 +26,7 @@
     <token name="@DADA_UNIQUES@">dada2_derep,dada2_dada,dada2_mergepairs</token>
 
     <!-- function to read dada2 data types
-         - derep, dada, and mergepairs are simply read as RDS 
+         - derep, dada, and mergepairs are simply read as RDS
          - sequence_table is a named integer matrix (rows=samples, columns=ASVs)
          - uniques is a named integer vector (columns=ASVs, only one rows)-->
     <token name="@READ_FOO@"><![CDATA[
@@ -48,7 +48,7 @@
     #end def
     ]]></token>
     <!-- function to write dada2 data types (the content or the R variable 'out' is written)
-         - derep, dada, and mergepairs are written as RDS 
+         - derep, dada, and mergepairs are written as RDS
          - sequence_table is a named integer matrix (rows=samples, columns=ASVs)
          - uniques is a named integer vector (columns=ASVs, only one rows)-->
     <token name="@WRITE_FOO@"><![CDATA[
@@ -61,7 +61,27 @@
         saveRDS(data, file=fname)
     }
 }
-    ]]></token> 
+    ]]></token>
+
+    <xml name="fastq_input" token_multiple="" token_collection_type="" token_argument_fwd="" token_argument_rev="">
+        <conditional name="paired_cond">
+            <param name="paired_select" type="select" label="Paired reads">
+                <option value="paired">paired - in a data set pair</option>
+                <option value="separate">paired - in two separate data sets</option>
+                <option value="single">single</option>
+            </param>
+            <when value="paired">
+                <param name="reads" argument="@ARGUMENT_FWD@/@ARGUMENT_REV@" type="data_collection" collection_type="@COLLECTION_TYPE@" format="fastq,fastq.gz" label="Paired short read data"/>
+            </when>
+            <when value="separate">
+                <param name="reads" argument="@ARGUMENT_FWD@" type="data" format="fastq,fastq.gz" multiple="@MULTIPLE@" label="Forward read data"/>
+                <param name="sdaer" argument="@ARGUMENT_REV@" type="data" format="fastq,fastq.gz" multiple="@MULTIPLE@" label="Reverse read data"/>
+            </when>
+            <when value="single">
+                <param name="reads" argument="@ARGUMENT_FWD@" type="data" format="fastq,fastq.gz" multiple="@MULTIPLE@" label="Short read data"/>
+            </when>
+        </conditional>
+    </xml>
 
     <!-- for filterAndTrim -->
     <xml name="trimmers">
@@ -69,7 +89,7 @@
             <param argument="truncQ" type="integer" value="2" min="0" label="Truncate reads at quality threshold" help="Truncate reads at the first instance of a quality score less than or equal to this threshold"/>
             <param argument="trimLeft" type="integer" value="0" min="0" label="Trim start of each read" help="The number of nucleotides to remove from the start of each read."/>
             <param argument="trimRight" type="integer" value="0" min="0" label="Trim end of each read" help="The number of nucleotides to remove from the end of each read"/>
-			<param argument="truncLen" type="integer" value="0" min="0" label="Truncate read length" help="Truncate reads after this amount of bases. Reads shorter than this are discarded. (default 0: no truncation)"/>
+            <param argument="truncLen" type="integer" value="0" min="0" label="Truncate read length" help="Truncate reads after this amount of bases. Reads shorter than this are discarded. (default 0: no truncation)"/>
         </section>
     </xml>
     <xml name="filters">
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dada2_species.loc	Tue May 28 12:13:45 2019 -0400
@@ -0,0 +1,10 @@
+# This is a sample file distributed with Galaxy that is used to define a
+# list of dada2 reference data sets for species assignment, using three
+# tab separated columns:
+#
+# <unique_build_id>	<display_name>	<fasta_file_path>
+#
+# Datasets can be retrieved from http://busco.ezlab.org/frame_wget.html
+#
+# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html
+test_buildid	test_displayname	${__HERE__}/reference_species.fa
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/dada2_taxonomy.loc	Tue May 28 12:13:45 2019 -0400
@@ -0,0 +1,10 @@
+# This is a sample file distributed with Galaxy that is used to define a
+# list of dada2 reference data sets for taxonomy assignment, using three
+# tab separated columns:
+#
+# <unique_build_id>	<display_name>	<fasta_file_path>	<taxlevels>
+#
+# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html
+# 
+# taxlevels is a comma separated list of taxonomy levels
+test_buildid	test_displayname	${__HERE__}/reference.fa	Level1,Level2,Level3,Level4,Level5
Binary file test-data/qualityProfile.pdf has changed
Binary file test-data/qualityProfileMultiple.pdf has changed
Binary file test-data/qualityProfileMultiple_rev.pdf has changed
Binary file test-data/qualityProfileSmallSample.pdf has changed
Binary file test-data/qualityProfile_rev.pdf has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.test	Tue May 28 12:13:45 2019 -0400
@@ -0,0 +1,11 @@
+<?xml version="1.0"?>
+<tables>
+    <table name="dada2_species" comment_char="#">
+        <columns>value, name, path</columns>
+        <file path="${__HERE__}/test-data/dada2_species.loc" />
+    </table>
+    <table name="dada2_taxonomy" comment_char="#">
+        <columns>value, name, path, taxlevels</columns>
+        <file path="${__HERE__}/test-data/dada2_taxonomy.loc" />
+    </table>
+</tables>